Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NikiforovAll/claude-code-rules --skill adr-plangit clone --depth 1 https://github.com/NikiforovAll/claude-code-rulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nikiforovall/claude-code-rules/adr-plan)<a href="https://agentmods.dev/skills/nikiforovall/claude-code-rules/adr-plan"><img src="https://agentmods.dev/badge/skills/nikiforovall/claude-code-rules/adr-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nikiforovall/claude-code-rules/adr-plan"><img src="https://agentmods.dev/badge/skills/nikiforovall/claude-code-rules/adr-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.00621 |
| Opus 5.5 | $0.00006 | $0.00248 |
| Sonnet 5.5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
adr-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Plan: Task Analysis → Architecture Decision Record
Analyze a task, explore the codebase, and produce an ADR with concrete implementation steps.
Phase 1: Analyze
- Read the task description, active plan, or task list
- Explore affected areas of the codebase — do it concurrently for independent modules
- Map blast radius — search for consumers of functions/types/routes being changed
- Identify alternatives worth considering (at least 2)
Do this silently.
Phase 2: Detect ADR Setup
Check if the project has an ADR directory:
ls docs/adr/ || ls adr/ || ls doc/adr/
- Found → use existing directory, detect next number from existing files
- Not found → run
npx adr init en, then proceed
Phase 3: Produce ADR Content
Write the ADR using npx adr new "<title>", then edit the generated file with the following structure:
# ADR-NNNN: [Title]
## Status
Proposed
## Context
[What problem are we solving? What constraints exist?]
## Decision
[What we chose and why]
## Alternatives Considered
| Option | Pros | Cons |
|--------|------|------|
| ... | ... | ... |
## Implementation Steps
### Step 1: [Description]
- **Files:** [files to create/modify]
- **Depends on:** [previous step or "none"]
- **Done when:** [concrete acceptance criteria]
### Step 2: [Description]
...
## Consequences
- [Positive and negative outcomes, tradeoffs accepted]
Guidelines
- Steps are ordered by dependency — each step lists what it depends on
- Steps are parallelizable when independent — note which steps can run concurrently
- Each step has concrete "done when" criteria — no vague outcomes
- Alternatives table is honest — include the option you chose and why others lost
- Keep it short. 1-2 pages max. No padding.
Phase 4: Present to User
Show the ADR content and the file path. The user may:
- Approve → ADR stays as-is
- Adjust → edit and re-present
- Cancel → delete the file
Important
- The ADR is a planning artifact, not documentation for posterity
- Steps should map naturally to work units (a team member could own one or more steps)
- If the task is too simple for an ADR (single file, obvious fix), say so and skip
- Do not write implementation code — this is planning only
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 25d ago First seen · 87 lines · 16 tokens per session scan A 3d4fa365e9a3
adr-plan is a skill published in the GitHub repository NikiforovAll/claude-code-rules (141 stars, last pushed 14d ago), licensed Apache-2.0. It adds 16 tokens to every session and 621 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
review-pr
Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…
researcher
Use when asked to create research documents, generate PDFs, make one-pagers, or create cheatsheets. Triggers: "research document", "generate PDF", "one-pager", "cheatsheet", "distinctive design". Provides HTML/Markdown/PDF with Terminal, Editorial, Corporate, Industrial, Fresh aesthetic presets.
svg-mastery
Expert knowledge for working with SVG (Scalable Vector Graphics) — optimization, embedding, animation, accessibility, responsive scaling, React integration, filters, and programmatic creation. Use when the user asks to "optimize SVG", "clean up SVG", "reduce SVG file size", "embed SVG in HTML", "inline SVG vs img…
demo-graphics
Dresses the Final Cut Pro finish of a demo video with Motion templates — MotionVFX DesignStudio elements downloaded through mExtension first, Final Cut Pro's built-in templates otherwise. Inventories what is installed (downloaded or only a placeholder), picks one look and one element per role from the footage — title…
demo-video
Orchestrates building a narrated demo video of a project — reads the codebase, writes a storyboard, prepares deterministic app state, drives the UI with Playwright to record clips (web and Electron, recorded by Playwright or by OBS), generates ElevenLabs voiceover, reconciles measured durations into a timeline, and…
icon-library
Fetch pre-made SVG icons from open-source icon libraries (Lucide, Heroicons, Tabler Icons) for use in websites, presentations, Figma designs, or any project. Use when the user asks to "add an icon", "use a search icon", "find an icon for settings", "get SVG icons", or needs clean SVG icons. NEVER draw icons manually …